Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems

TL;DR

This paper introduces a recourse algorithm that models data distribution to generate minimal, actionable changes for individuals to improve outcomes in black-box decision systems, applicable to classification and causal models.

Contribution

It proposes a novel recourse method that leverages data manifold modeling, providing realistic and actionable explanations for black-box systems, filling gaps in fairness and counterfactual explanation literature.

Findings

Algorithm effectively generates minimal changes for outcome improvement.

Applicable to both supervised classification and causal decision systems.

Demonstrates practical use in real-world decision-making scenarios.

Abstract

Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set of changes a person can undertake in order to improve their outcome. We propose a recourse algorithm that models the underlying data distribution or manifold. We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome. This mechanism can be easily used to provide recourse for any differentiable machine learning based decision making system. Further, the resulting algorithm is shown to be applicable to both supervised classification and causal decision making systems. Our work attempts to fill gaps in existing fairness literature that have primarily focused on discovering and/or algorithmically enforcing fairness constraints on decision making systems. This work also provides an alternative approach to generating counterfactual explanations.